acl-management

Pass

Audited by Gen Agent Trust Hub on Aug 3, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes the SN-Execute-Background-Script tool to run arbitrary server-side Javascript (GlideScript) on the ServiceNow platform. Evidence found in Phase 4 and 5 includes scripts for resetting the ACL cache, tracing evaluation logic, and checking user roles.
  • [PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection.
  • Ingestion points: Untrusted data enters the agent context through the SN-Query-Table and SN-Get-Table-Schema tools when reading from tables like sys_security_acl.
  • Boundary markers: The instructions lack delimiters or explicit warnings to the agent to ignore instructions embedded within the retrieved table data (e.g., within the description or script fields of an ACL record).
  • Capability inventory: The skill possesses high-privilege capabilities including record creation (SN-Create-Record), updates (SN-Update-Record), and arbitrary script execution (SN-Execute-Background-Script).
  • Sanitization: There is no evidence of filtering or sanitization of content retrieved from the ServiceNow instance before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 3, 2026, 02:23 PM
Security Audit — agent-trust-hub — acl-management